# Not full-text search wearing a trenchcoat.

Canonical source: https://maguyva.ai/beyond-rag

License: text under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); code samples under [MIT-0](https://opensource.org/license/mit-0); the Maguyva name, logos, brand assets and other code are not covered. Details: [maguyva.ai/license](https://maguyva.ai/license).

Code needs more than semantic chunks. Maguyva fuses five retrieval modes into one ranked answer, grounded in the real repo.

RAG over code chunks finds text that looks similar, not code that is actually connected. Maguyva ranks semantic, structural (AST), graph, and text search into one answer, and every result points at a real file and line.

- [Index your first repo](https://app.maguyva.ai/auth/sign-up?plan=free)
- [Read the docs](https://maguyva.ai/docs)

free plan: 3 repos, 50K indexed lines, no card.

## Semantic, structural, graph, text, grounded

*// five modes*

Five retrieval lenses ranked into one answer. Not single-mode RAG over chunks.

## File paths and line numbers

*// grounded*

Every result points at real code you can open and verify. No confident hallucination.

## Remote MCP, 285 languages

*// any client*

Works with Claude, Codex, Cursor, and any MCP client. No local indexer to run.

## Try it on a repo where you can verify.

Index one repo you already know and ask one question you can check against the source.

01. **Index a repo you know**: Pick one where you can verify the answer against the source. Free tier: 3 repos, 50K indexed lines.
02. **Connect over MCP**: Claude, Codex, Cursor, or any MCP client. One remote server, no embeddings to manage.
03. **Ask a question RAG usually fumbles**: Find the real implementation, not the test mock. Watch five modes rank it first.

## Five fused retrieval modes, one ranked answer.

Start free. See why multi-lens retrieval beats single-mode RAG on real code. No credit card, no sales call.

- [Index your first repo](https://app.maguyva.ai/auth/sign-up?plan=free)
- [Read the docs](https://maguyva.ai/docs)